paper-with-me

Papers

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory

2023-07-09 · NeurIPS 2023 11

Cohen et al. (2021) empirically study the evolution of the largest eigenvalue of the loss Hessian, also known as sharpness, along the gradient descent (GD) trajectory and observe the Edge of Stability (EoS) phenomenon. The sharpness increases at the early phase of training (referred to as progressive sharpening), and eventually saturates close to the threshold of $2 / \text{(step size)}$. In this paper, we start by demonstrating through empirical studies that when the EoS phenomenon occurs, different GD trajectories (after a proper reparameterization) align on a specific bifurcation diagram independent of initialization. We then rigorously prove this trajectory alignment phenomenon for a two-layer fully-connected linear network and a single-neuron nonlinear network trained with a single data point. Our trajectory alignment analysis establishes both progressive sharpening and EoS phenomena, encompassing and extending recent findings in the literature.

📄 PDF Abstract BibTeX arXiv:2307.04204

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability

2025-07-17 · Kaiqi Jiang, Jeremy Cohen, Yuanzhi Li arxiv

The study of Neural Tangent Kernels (NTKs) in deep learning has drawn increasing attention in recent years. NTKs typically actively change during training and are related to feature learning. In parallel, recent work on …

Investigating the Edge of Stability Phenomenon in Reinforcement Learning

2023-07-09 · Rares Iordan, Marc Peter Deisenroth, Mihaela Rosca

Recent progress has been made in understanding optimisation dynamics in neural networks trained with full-batch gradient descent with momentum with the uncovering of the edge of stability phenomenon in supervised learnin…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

SAM operates far from home: eigenvalue regularization as a dynamical phenomenon

2023-02-17 · Atish Agarwala, Yann N. Dauphin

The Sharpness Aware Minimization (SAM) optimization algorithm has been shown to control large eigenvalues of the loss Hessian and provide generalization benefits in a variety of settings. The original motivation for SAM …

Towards Critical Clearing Time Sensitivity for DAE Systems with Singularity

2020-02-20

Standard power system models are parameter dependent differential-algebraic equation (DAE) type. Following a transient event, voltage collapse can occur as a bifurcation of the transient load flow solutions which is mark…

Sensitivity

The Origin of Edge of Stability

2026-04-22 · Elon Litman arxiv

Full-batch gradient descent on neural networks drives the largest Hessian eigenvalue to the threshold $2/η$, where $η$ is the learning rate. This phenomenon, the Edge of Stability, has resisted a unified explanation: exi…